Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generalized Planning on Childsnack
Loading...
100
Scale
Explicitly regularized Q-value policy (Ω^Exp.)
5.36
29.93
54.5
79.07
Mar 18, 2026
Scale
SCov
Updated 1mo ago
Evaluation Results
Method
Method
Links
Scale
SCov
Explicitly regularized Q-value policy (Ω^Exp.)
Architecture=R-GNN
2026.03
100
93
Heuristically regularized Q-value policy (Ω^Heu.)
Architecture=R-GNN
2026.03
100
93
Explicitly regularized Q-value policy (Ω^Exp.)
Architecture=OAE
2026.03
100
65.8
Heuristically regularized Q-value policy (Ω^Heu.)
Architecture=OE
2026.03
98
46.9
Heuristically regularized Q-value policy (Ω^Heu.)
Architecture=OAE
2026.03
83
41.5
Explicitly regularized Q-value policy (Ω^Exp.)
Architecture=OE
2026.03
82
43.1
State-value policy (V)
Architecture=R-GNN
2026.03
71
43.4
Vanilla Q-value policy (Q)
Architecture=OAE
2026.03
36
14.9
State-value policy (V)
Architecture=OAE
2026.03
31
15.9
State-value policy (V)
Architecture=OE
2026.03
26
12
Vanilla Q-value policy (Q)
Architecture=R-GNN
2026.03
16
4.2
Vanilla Q-value policy (Q)
Architecture=OE
2026.03
9
0.2
Feedback
Search any
task
Search any
task